Metal-organic frameworks (MOFs) exhibit significant potential for the adsorption of volatile organic compounds (VOCs) due to their tunable pore structures and high specific surface areas. However, identifying high-performing MOFs within the vast structural space remains challenging, primarily due to unclear structure–performance relationships. Moreover, existing studies often overlook realistic adsorption scenarios that involve coexisting atmospheric components such as O2, N2, and water vapor, and rarely address capacity–selectivity trade-offs or conducted systematic comparisons of model performance. Herein, we developed a data-driven machine learning framework integrating multi-model comparisons, stacking ensemble modeling, and interpretability analyses for predicting the adsorption performance of MOFs for airborne toluene with high accuracy. The stacking model, comprising eight complementary base models and a multilayer perceptron (MLP) as the meta-learner, demonstrated an enhanced capability to capture complex nonlinear relationships between descriptors and performance, achieving superior predictive accuracy (R2 = 0.922, RMSE = 0.186) compared to the best-performing individual model, CatBoost (R2 = 0.890, RMSE = 0.326). Furthermore, by incorporating SHAP, PDP, and feature interaction analyses, this study elucidated the synergistic regulatory mechanisms associated with key structural descriptors. Statistical analysis further revealed that the structural parameters of high-performing MOFs exhibited significant convergence, with metal centers such as Cu and their open metal sites (OMS) quantitatively identified as critical performance-enhancing factors. Finally, the stacking model was successfully deployed as an interactive web platform that enables real-time prediction and visual interpretability of MOF performance, serving as a practical tool for the efficient screening of MOF candidates for airborne toluene adsorption.
| [1] |
F. Meng, M. Song, Y. Wei, and Y. Wang, “The Contribution of Oxygen-Containing Functional Groups to the Gas-Phase Adsorption of Volatile Organic Compounds With Different Polarities Onto Lignin-Derived Activated Carbon Fibers,” Environmental Science and Pollution Research 26, no. 7 (2019): 7195–7204.
|
| [2] |
Z. Zhang, Z. Jiang, and W. Shangguan, “Low-Temperature Catalysis for VOCs Removal in Technology and Application: A State-Of-The-Art Review,” Catalysis Today 264 (2016): 270–278.
|
| [3] |
Y. Sun, J. Hou, R. Cheng, Y. Sheng, X. Zhang, and J. Sundell, “Indoor Air Quality, Ventilation and Their Associations With Sick Building Syndrome in Chinese Homes,” Energy and Buildings 197 (2019): 112–119.
|
| [4] |
M. A. Lillo-Ródenas, A. J. Fletcher, K. M. Thomas, D. Cazorla-Amorós, and A. Linares-Solano, “Competitive Adsorption of a Benzene–Toluene Mixture on Activated Carbons at Low Concentration,” Carbon 44, no. 8 (2006): 1455–1463.
|
| [5] |
T. Ban, L. Yu, R. Li, et al., “Microenvironment Modulation for Electronic Structure of Atomically Dispersed IR Species in Metal–Organic Frameworks Toward Boosting Catalytic DCPD Hydrogenation Performance,” Carbon Neutralization 4, no. 2 (2025): e70004.
|
| [6] |
S. Zhou, H. Li, H. Gao, et al., “Recent Advances in Metal-Loaded MOFs Photocatalysts: From Single Atom, Cluster to Nanoparticle,” Chinese Chemical Letters 36, no. 1 (2025): 110142.
|
| [7] |
X. Zhang, F. Bi, Z. Zhu, et al., “The Promoting Effect of H2O on Rod-Like MnCeOx Derived From MOFs for Toluene Oxidation: A Combined Experimental and Theoretical Investigation,” Applied Catalysis, B: Environmental 297 (2021): 120393.
|
| [8] |
H. Tan, Y. Teng, and G. Shan, “High Throughput Computational Screening and Interpretable Machine Learning for Iodine Capture of Metal-Organic Frameworks,” npj Computational Materials 11, no. 1 (2025): 115.
|
| [9] |
X. Bai, Z. Shi, H. Xia, et al., “Machine-Learning-Assisted High-Throughput Computational Screening of Metal–Organic Framework Membranes for Hydrogen Separation,” Chemical Engineering Journal 446 (2022): 136783.
|
| [10] |
N. P. Makhanya, M. Kumi, C. Mbohwa, and B. Oboirien, “Application of Machine Learning in Adsorption Energy Storage Using Metal Organic Frameworks: A Review,” Journal of Energy Storage 111 (2025): 115363.
|
| [11] |
W. Xu, B. Tu, Q. Liu, et al., “Anisotropic Reticular Chemistry,” Nature Reviews Materials 5, no. 10 (2020): 764–779.
|
| [12] |
X. Zheng, S. Rehman, and P. Zhang, “Room Temperature Synthesis of Monolithic MIL-100(Fe) in Aqueous Solution for Energy-Efficient Removal and Recovery of Aromatic Volatile Organic Compounds,” Journal of Hazardous Materials 442 (2023): 129998.
|
| [13] |
T. Islamoglu, Z. Chen, M. C. Wasson, et al., “Metal–Organic Frameworks Against Toxic Chemicals,” Chemical Reviews 120, no. 16 (2020): 8130–8160.
|
| [14] |
N. C. Burtch, H. Jasuja, and K. S. Walton, “Water Stability and Adsorption in Metal–Organic Frameworks,” Chemical Reviews 114, no. 20 (2014): 10575–10612.
|
| [15] |
P. Z. Moghadam, D. Fairen-Jimenez, and R. Q. Snurr, “Efficient Identification of Hydrophobic MOFs: Application in the Capture of Toxic Industrial Chemicals,” Journal of Materials Chemistry A 4, no. 2 (2016): 529–536.
|
| [16] |
B. Selvaratnam and R. T. Koodali, “Machine Learning in Experimental Materials Chemistry,” Catalysis Today 371 (2021): 77–84.
|
| [17] |
X. Liu, R. Wang, X. Wang, and D. Xu, “High-Throughput Computational Screening and Machine Learning Model for Accelerated Metal–Organic Frameworks Discovery in Toluene Vapor Adsorption,” Journal of Physical Chemistry C 127, no. 23 (2023): 11268–11282.
|
| [18] |
L. Zhang, Q. Huang, L. Li, et al., “Automatic Machine Learning Combined With High-Throughput Computational Screening of Hydrophobic Metal–Organic Frameworks for Capture of Methanol and Ethanol From the Air,” ACS ES&T Engineering 4, no. 1 (2024): 115–127.
|
| [19] |
R. Ou, W. Zhu, L. Li, et al., “Boosted Capture of Volatile Organic Compounds in Adsorption Capacity and Selectivity by Rationally Exploiting Defect-Engineering of UiO-66(Zr),” Separation and Purification Technology 266 (2021): 118087.
|
| [20] |
Z. Liu, W. Li, H. Liu, X. Zhuang, and S. Li, “Research Progress of High-Throughput Computational Screening of Metal-Organic Frameworks,” Acta Chimica Sinica 77, no. 4 (2019): 323.
|
| [21] |
K. M. Jablonka, D. Ongari, S. M. Moosavi, and B. Smit, “Big-Data Science in Porous Materials: Materials Genomics and Machine Learning,” Chemical Reviews 120, no. 16 (2020): 8066–8129.
|
| [22] |
J. Lin, D. Zhao, S. Lu, et al., “Conversational Large-Language-Model Artificial Intelligence Agent for Accelerated Synthesis of Metal–Organic Frameworks Catalysts in Olefin Hydrogenation,” ACS Nano 19, no. 26 (2025): 23840–23858.
|
| [23] |
J. Lin, T. Ban, T. Li, et al., “Machine-Learning-Assisted Intelligent Synthesis of UiO-66(Ce): Balancing the Trade-Off Between Structural Defects and Thermal Stability for Efficient Hydrogenation of Dicyclopentadiene,” Materials Genome Engineering Advances 2, no. 3 (2024): e61.
|
| [24] |
J. Xie, “Prospects of Materials Genome Engineering Frontiers,” Materials Genome Engineering Advances 1, no. 2 (2023): e17.
|
| [25] |
Y. G. Chung, E. Haldoupis, B. J. Bucior, et al., “Advances, Updates, and Analytics for the Computation-Ready, Experimental Metal–Organic Framework Database: CoRE MOF 2019,” Journal of Chemical & Engineering Data 64, no. 12 (2019): 5985–5998.
|
| [26] |
M. Jahandar Lashaki, M. Fayaz, S. Niknaddaf, and Z. Hashisho, “Effect of the Adsorbate Kinetic Diameter on the Accuracy of the Dubinin–Radushkevich Equation for Modeling Adsorption of Organic Vapors on Activated Carbon,” Journal of Hazardous Materials 241–242 (2012): 154–163.
|
| [27] |
C. Wang, X. Liu, N. Keser Demir, J. P. Chen, and K. Li, “Applications of Water Stable Metal–Organic Frameworks,” Chemical Society Reviews 45, no. 18 (2016): 5107–5134.
|
| [28] |
W. Xue, J. Wang, H. Huang, and D. Mei, “Structural and Hydrolytic Stability of Coordinatively Unsaturated Metal–Organic Frameworks M3(BTC)2 (M = Cu, Co, Mn, Ni, and Zn): A Combined DFT and Experimental Study,” Journal of Physical Chemistry C 125, no. 10 (2021): 5832–5847.
|
| [29] |
D. Dubbeldam, S. Calero, D. E. Ellis, and R. Q. Snurr, “RASPA: Molecular Simulation Software for Adsorption and Diffusion in Flexible Nanoporous Materials,” Molecular Simulation 42, no. 2 (2016): 81–101.
|
| [30] |
T. F. Willems, C. H. Rycroft, M. Kazi, J. C. Meza, and M. Haranczyk, “Algorithms and Tools for High-Throughput Geometry-Based Analysis of Crystalline Porous Materials,” Microporous and Mesoporous Materials 149, no. 1 (2012): 134–141.
|
| [31] |
Z. Qie, X. Lu, Z. Wang, et al., “Transformation in Ring Topology of Beta Zeolite Induced by Chelation: Implications for CO2 and Toluene Adsorption Under Humid Conditions,” Separation and Purification Technology 378 (2025): 134677.
|
| [32] |
R. B. Getman, Y. S. Bae, C. E. Wilmer, and R. Q. Snurr, “Review and Analysis of Molecular Simulations of Methane, Hydrogen, and Acetylene Storage in Metal–Organic Frameworks,” Chemical Reviews 112, no. 2 (2012): 703–723.
|
| [33] |
A. K. Rappe, C. J. Casewit, K. S. Colwell, W. A. Goddard, and W. M. Skiff, “UFF, a Full Periodic Table Force Field for Molecular Mechanics and Molecular Dynamics Simulations,” Journal of the American Chemical Society 114, no. 25 (1992): 10024–10035.
|
| [34] |
C. D. Wick, M. G. Martin, and J. I. Siepmann, “Transferable Potentials for Phase Equilibria. 4. United-Atom Description of Linear and Branched Alkenes and Alkylbenzenes,” Journal of Physical Chemistry B 104, no. 33 (2000): 8008–8016.
|
| [35] |
P. P. Ewald, “Die Berechnung Optischer und Elektrostatischer Gitterpotentiale,” Annalen der Physik 369, no. 3 (1921): 253–287.
|
| [36] |
T. Akiba, S. Sano, T. Yanase, et al., “Optuna: A Next-Generation Hyperparameter Optimization Framework,” preprint, arXiv, 2019.
|
| [37] |
F. Pedregosa, G. Varoquaux, A. Gramfort, et al., “Scikit-Learn: Machine Learning in Python,” preprint, arXiv, 2018.
|
| [38] |
D. Yuan, D. Zhao, D. Sun, and H. Zhou, “An Isoreticular Series of Metal–Organic Frameworks With Dendritic Hexacarboxylate Ligands and Exceptionally High Gas-Uptake Capacity,” Angewandte Chemie International Edition 49, no. 31 (2010): 5357–5361.
|
| [39] |
Z. Qiao, Y. Yan, Y. Tang, H. Liang, and J. Jiang, “Metal–Organic Frameworks for Xylene Separation: From Computational Screening to Machine Learning,” The Journal of Physical Chemistry C 125, no. 14 (2021): 7839–7848.
|
| [40] |
X. Zhang, Z. Chen, X. Liu, et al., “A Historical Overview of the Activation and Porosity of Metal–Organic Frameworks,” Chemical Society Reviews 49, no. 20 (2020): 7406–7427.
|
| [41] |
R. R. Maldonado, X. Zhang, S. Hanna, et al., “Squeezing the Box: Isoreticular Contraction of Pyrene-Based Linker in a Zr-Based Metal–Organic Framework for Xe/Kr Separation,” Dalton Transactions 49, no. 20 (2020): 6553–6556.
|
| [42] |
T. Chen and C. Guestrin, “XGBoost: A Scalable Tree Boosting System,” in Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (ACM, 2016), 785–794.
|
| [43] |
J. T. Hancock and T. M. Khoshgoftaar, “CatBoost for Big Data: An Interdisciplinary Review,” Journal of Big Data 7, no. 1 (2020): 94.
|
| [44] |
J. H. Friedman, “Greedy Function Approximation: A Gradient Boosting Machine,” Annals of Statistics 29, no. 5 (2001): 1189–1232.
|
| [45] |
A. Goldstein, A. Kapelner, J. Bleich, and E. Pitkin, “Peeking Inside the Black Box: Visualizing Statistical Learning With Plots of Individual Conditional Expectation,” Journal of Computational and Graphical Statistics 24, no. 1 (2015): 44–65.
|
| [46] |
R. K. Sinha, “Book Review: Christoph Molnar. 2020. Interpretable Machine Learning: A Guide for Making Black Box Models Explainable,” Metamorphosis: A Journal of Management Research 23, no. 1 (2024): 92–93.
|
| [47] |
S. Lundberg and S. I. Lee, “A Unified Approach to Interpreting Model Predictions,” preprint, arXiv, 2017.
|
| [48] |
M. Zhu, P. Hu, Z. Tong, Z. Zhao, and Z. Zhao, “Enhanced Hydrophobic MIL(Cr) Metal-Organic Framework With High Capacity and Selectivity for Benzene VOCs Capture From High Humid Air,” Chemical Engineering Journal 313 (2017): 1122–1131.
|
| [49] |
D. Lozano-Castelló, D. Cazorla-Amorós, A. Linares-Solano, and D. F. Quinn, “Influence of Pore Size Distribution on Methane Storage at Relatively Low Pressure: Preparation of Activated Carbon With Optimum Pore Size,” Carbon 40, no. 7 (2002): 989–1002.
|
| [50] |
H. Furukawa, K. E. Cordova, M. O'Keeffe, and O. M. Yaghi, “The Chemistry and Applications of Metal-Organic Frameworks,” Science 341, no. 6149 (2013): 1230444.
|
| [51] |
X. Li, L. Zhang, Z. Yang, P. Wang, Y. Yan, and J. Ran, “Adsorption Materials for Volatile Organic Compounds (VOCs) and the Key Factors for VOCs Adsorption Process: A Review,” Separation and Purification Technology 235 (2020): 116213.
|
| [52] |
Ü. Kökçam-Demir, A. Goldman, L. Esrafili, et al., “Coordinatively Unsaturated Metal Sites (Open Metal Sites) in Metal–Organic Frameworks: Design and Applications,” Chemical Society Reviews 49, no. 9 (2020): 2751–2798.
|
| [53] |
J. Bentley, G. S. Foo, M. Rungta, et al., “Effects of Open Metal Site Availability on Adsorption Capacity and Olefin/Paraffin Selectivity in the Metal–Organic Framework Cu3(BTC)2,” Industrial & Engineering Chemistry Research 55, no. 17 (2016): 5043–5053.
|
| [54] |
M. A. Syzgantseva, C. P. Ireland, F. M. Ebrahim, B. Smit, and O. A. Syzgantseva, “Metal Substitution as the Method of Modifying Electronic Structure of Metal–Organic Frameworks,” Journal of the American Chemical Society 141, no. 15 (2019): 6271–6278.
|
| [55] |
Q. Li, W. Zhang, O. Š. Miljanić, et al., “Docking in Metal-Organic Frameworks,” Science 325, no. 5942 (2009): 855–859.
|
| [56] |
K. Hornik, M. Stinchcombe, and H. White, “Multilayer Feedforward Networks Are Universal Approximators,” Neural Networks 2, no. 5 (1989): 359–366.
|
| [57] |
T. Xie and J. C. Grossman, “Crystal Graph Convolutional Neural Networks for an Accurate and Interpretable Prediction of Material Properties,” Physical Review Letters 120, no. 14 (2018): 145301.
|
| [58] |
M. R. Dobbelaere, P. P. Plehiers, R. Van De Vijver, C. V. Stevens, and K. M. Van Geem, “Machine Learning in Chemical Engineering: Strengths, Weaknesses, Opportunities, and Threats,” Engineering 7, no. 9 (2021): 1201–1211.
|
RIGHTS & PERMISSIONS
2025 The Author(s). Carbon Neutralization published by Wenzhou University and John Wiley & Sons Australia, Ltd.
PDF
